RightNow-AI/openfang
OpenFang is an open-source agent operating system, built in Rust, designed to facilitate the management and orchestration of AI agents.
Awesome AI Agents › AI Agent Operating System
AGNT positions itself as an operating system for AI work rather than a single agent framework. It ships as a cross-platform desktop application built on Electron with a Vue front end, an Express backend that can also be self-hosted or run in Docker, and SQLite for local storage, so conversations, workflow definitions, memory and run traces stay on the user's machine. Four ways of working sit side by side: interactive chat when a task needs judgement, visual workflows built on an unbounded canvas when a process must repeat reliably, goals that let the system keep working toward an outcome over time, and delegation to sub-agents when parts of a job should run in parallel. Around those the app provides persistent memory, a library of more than sixty built-in tools, support for over fifteen model providers, Model Context Protocol integration for external tool servers, a plugin system with starter templates and an asset marketplace, plus evaluation runs and execution traces so that agent behaviour can be inspected and compared between versions instead of judged by impression. An HTTP API and messaging layer let other programs drive the same workspace. The stated aim is to make AI work durable, inspectable, repeatable and improvable: a workflow that succeeded once can be replayed, a trace explains why a run went the way it did, and evals measure whether a change helped. Installation is either a prebuilt binary for Windows, macOS or Linux with no terminal step, a build from source on Node 18 or newer, or a Docker deployment. It targets people who want to build and operate agents on their own hardware, keep data and API keys local, and use a visual builder alongside code.
https://github.com/agnt-gg/agnt
OpenFang is an open-source agent operating system, built in Rust, designed to facilitate the management and orchestration of AI agents.
A comprehensive repository showcasing practical examples, tutorials, and tools for building powerful AI applications using large language models and various AI agent frameworks.
QuantDinger is an open-source AI trading operating system designed for independent traders, Python strategy authors, and small teams, offering backtesting, live trading, and multi-agent research ca...
MemOS is an operating system for Large Language Models that enhances their capabilities with long-term memory, enabling more context-aware, consistent, and personalized AI interactions through a modular and extensible memory architecture.
HolaOS is a local-first, AI-powered desktop agent that learns your work context, integrates with over 100 workplace tools, and manages memory efficiently to provide proactive assistance without for...
mcp-use is an open-source unified client library that enables seamless integration of any LangChain-supported LLM with MCP servers to build custom agents with tool access.
Astrid is a portable, capability-secure operating system for composable software components, providing an OS-grade boundary for AI agents and other untrusted code via WebAssembly capsules.
AutoAgent is a fully-automated, zero-code framework for creating and deploying LLM agents using natural language, featuring top GAIA benchmark performance and broad LLM support.